Approximate Nearest Neighbor Search in high dimensional space is essential in DB and IR. Recently, NSG provides attractive theoretical analysis and achieves state-of-the-art performance. However, we find there are several limitations with NSG. In the theoretical aspect, NSG has no theoretical guarantee on searching for neighbors of not-in-database queries. In application, NSG is too sparse and thus has an inferior search performance. In addition, NSG's indexing complexity is also too high. To address above problems, we propose the Satellite System Graphs (inspired by the message transfer mechanism of the communication satellite system) and its approximation NSSG. Specifically, Satellite System Graphs define a new family of MSNETs in which the out-edges of each node are distributed evenly in all directions, and each node builds effective connections to its neighborhood omnidirectionally, whereupon we derive SSG's excellent theoretical properties for both in-database queries and not-in-database queries. We can adaptively adjust the sparsity of an SSG with a hyper-parameter to optimize the search performance. Further, NSSG is proposed to reduce the indexing complexity of the SSG for large-scale applications. Both theoretical and extensive experimental analysis are provided to demonstrate the strengths of the proposed approach over the state-of-the-art algorithms.We study network pruning which aims to remove redundant channels/kernels and accelerate the inference of deep networks. Existing pruning methods either train from scratch with sparsity constraints or minimize the reconstruction error between the feature maps of the pre-trained models and the compressed ones. Both strategies suffer from some limitations the former kind is computationally expensive and difficult to converge, while the latter kind optimizes the reconstruction error but ignores the discriminative power of channels. In this paper, we propose a discrimination-aware channel pruning (DCP) method to choose the channels that actually contribute to the discriminative power. Based on DCP, we further propose several techniques to improve the optimization efficiency. Note that the parameters of a channel (3D tensor) may contain redundant kernels (each with a 2D matrix). To solve this issue, we propose a discrimination-aware kernel pruning (DKP) method to select the kernels with promising discriminative power. Experiments on image classification and face recognition demonstrate the effectiveness of our methods. For example, on ILSVRC-12, the resultant ResNet-50 with 30% reduction of channels even outperforms the baseline model by 0.36% on Top-1 accuracy. https://www.selleckchem.com/products/tucidinostat-chidamide.html The pruned MobileNetV1 and MobileNetV2 achieve 1.93x and 1.42x inference acceleration on a mobile device, respectively, with negligible performance degradation.Changes in ultrasound backscatter energy (CBE) imaging can monitor thermal therapy. Catheter-based ultrasound (CBUS) can treat deep tumors with precise spatial control of energy deposition and ablation zones, of which CBE estimation can be limited by low contrast and robustness due to small or inconsistent changes in ultrasound data. This study develops a multi-spatiotemporal compounding CBE (MST-CBE) imaging approach for monitoring specific to CBUS thermal therapy.
Ex vivo thermal ablations were performed with stereotactic positioning of a 180 directional CBUS applicator, temperature monitoring probes, endorectal US probe, and subsequent lesion sectioning and measurement. Five frames of raw radiofrequency data were acquired throughout in 15s intervals. Using window-by-window estimation methods, absolute and positive components of MST-CBE images at each point were obtained by the compounding ratio of squared envelope data within an increasing spatial size in each short-time window.
Compared with conventional US, Nakagami, and CBE imaging, the detection contrast and robustness quantified by tissue-modification-ratio improved by 37.24.7 (p&lt;0.001), 37.55.2 (p&lt;0.001), and 6.44.0 dB (p&lt;0.05) in the MST-CBE imaging, respectively. Correlation coefficient and bias between cross-sectional dimensions of the ablation zones measured in tissue sections and estimated from MST-CBE were up to 0.91 (p&lt;0.001) and -0.02 mm2, respectively.
The MST-CBE approach can monitor the detailed changes within target tissues and effectively characterize the dimensions of the ablation zone during CBUS energy deposition.
The MST-CBE approach could be practical for improved accuracy and contrast of monitoring and evaluation for CBUS thermal therapy.
The MST-CBE approach could be practical for improved accuracy and contrast of monitoring and evaluation for CBUS thermal therapy.Restoration of elbow flexion is one of the key components of adult brachial plexus surgery. Nerve transfers are routinely used to attain elbow flexion.
This study aims to quantify the recovery of elbow flexion power and to compare the outcome following single nerve transfer and double nerve transfer to branches of the musculocutaneous nerve in adult traumatic brachial plexus injury.
We conducted a retrospective cohort study of patients with traumatic upper brachial plexus injury who underwent nerve transfer of the musculocutaneous nerve with either Ulnar nerve fascicles (SN) or both Ulnar and Median nerve fascicles (DN) for restoring elbow flexion. Patients with a minimum follow up of 18 months after surgery were included in this study. Elbow flexion strength was quantified using a force transducer and software module and the results were compared between the two groups.
The median strength of elbow flexion was 14.3 Newton meter. In the SN group, the mean strength of elbow flexion was 5.4±5 Nm, and for DN group it was 20.4±9.9 Nm. Elbow flexion strength following DN procedure was significantly better when compared with SN.
The additional nerve transfer of median nerve fascicles with musculocutaneous nerve branch to the brachialis muscle does not add clinically obvious morbidity to the patient but has definite benefit as observed in this study. We advocate double fascicular nerve transfer for elbow flexion in upper brachial plexus injuries if the median and ulnar nerve functions are normal.
The additional nerve transfer of median nerve fascicles with musculocutaneous nerve branch to the brachialis muscle does not add clinically obvious morbidity to the patient but has definite benefit as observed in this study. We advocate double fascicular nerve transfer for elbow flexion in upper brachial plexus injuries if the median and ulnar nerve functions are normal.